The followings are the projects I’ve been working on Github. I tried to put the most recent one up-front, but sometimes I go back and forward from one to another.
NVIDIA Jetson TX1 OpenCV 101 Tutorials: Here you will found the code from the OpenCV 101 tutorials. The tutorials a bit old and there are a couple of things that need to be fixed to be implemented with OpenCV 3.3.1.
ROS Ignite Academy : ROS in 5 Days projects: I am playing with ROS Ignite Academy and ROS. This repo contains all the code I wrote there.
Udacity’s Deep Learning Nanodegree - SageMaker Deployment: Contains a few tutorials, mini projects and a project using SageMaker for NPL.
DJI Service: DJI Mobile Service SDK on an Android Things application.
3D Estimation: Extended Kalman Filter(EKF) implemented with C++. we need to fusion noisy GPS, IMU, and compass(magnetometer) to estimate current drone position, velocity, and yaw.
3D Quadrotor Controller: Implement and tune a cascade PID controller(C++) for drone trajectory tracking.
3D Motion Planning: Planning and executing a trajectory of a drone in an urban environment.
Backyard Flyer: Control a simulated drone using python to fly in a square trajectory in a backyard.
Capstone: Create a set of ROS packages to drive Carla, Udacity’s self-driving car. This ran in a real car!
Functional Safety: Functional safety documentation for a Lane Assistance system under ISO 26262.
Semantic Segmentation: Semantic segmentation using fully convolutional networks(FCN).
Path Planning: Path planning algorithms to drive a car on a highway using Udacity’s simulator.
Model Predictive Control: Model Predictive Control (MPC) implementation to control a car in Udacity’s simulator.
PID: PID controller to control a car on Udacity’s simulator.
Kidnapped Vehicle => Particle filter: Kidnapped Vehicle project. Particle Filter applied to A Kidnapped robot problem.
Unscented Kalman Filter: Unscented Kalman Filter Implementation with C++. A simulator generates noisy RADAR and LIDAR measurements of the position and velocity of an object, and the Unscented Kalman Filter[UKF] must fusion those measurements to predict the location of the object.
Extended Kalman Filter: Extended Kalman Filter Implementation with C++. A simulator generates noisy RADAR and LIDAR measurements of the position and velocity of an object, and the Extended Kalman Filter[EKF] must fusion those measurements to predict the location of the object.
Vehicle Detection: Vehicle Detection using Linear SVM classifier and computer vision.
Advanced Lane Lines Finder: Advance Lane Line Finder on a Video Stream.
Behavioral Cloning: Behavioral Cloning. Trying to reproduce my driving behavior in a simulated environment using LeNet and Keras.
Traffic Sign Classifier: Traffic Sign Classifier. The project consists of training a Convolutional Neural Network to recognize traffic signs.
Lane Lines Finder: Finding Lane Lines on the Road. This project consists of algorithms to identify lane lines on the road on a video. The video is taken from a camera at the center of a vehicle.
Kamon Logstash back-end: Kamon-stash back-end module. Using ELK(Elasticsearch-Logstash-Kibana) for data collection and visualization for Kamon.
Advent of Code: Problem Advent of Code site problems solutions with Scala.
Family Playground: Proof of concept for a REST-full service using Scala/Play, Elasticseach and Couchbase.
Airplane Adventures: Using Scala to process the information of a Dump1090/Flightaware receiver.